Hopper (G) 1.2: adapter, calibration map, checksums and model card

CHECKSUMS.txt

@@ -0,0 +1,3 @@
+5e6c17beae26839e65be9805023c46397a073af83edad87c29b111d5d8f1c490  adapter_config.json
+8813cb2a1e44184bcdae017ace49cfc7cb00738c611423b6198c4b5ea553deaf  adapter_model.safetensors
+217a2af396320c8a279e2f915fe17e67184cdf577668eb38147775184c259ade  hopper.json

README.md

@@ -0,0 +1,46 @@
+---
+license: other
+license_name: research-and-demo
+base_model: Qwen/Qwen3.5-4B
+library_name: peft
+tags: [decision, classification, calibration, lora]
+---
+
+# Hopper (G)
+
+A general-purpose version of [Hopper](https://huggingface.co/HopitAI/hopper): a LoRA adapter for Qwen3.5-4B that
+answers typed decision questions in one forward pass by reading the probability of each option letter, with a
+per-kind calibration map. Served with the Hopper code at https://github.com/hopit-ai/hopper (tag `g-1.2.0`).
+
+**Research and demo use only.** This adapter continues training from Hopper 1.0's adapter, whose training data
+included passages from RACE (non-commercial research only), and its training data also includes material made with
+LLM-based generation. Do not use it commercially.
+
+## What it is
+
+- Base: Qwen/Qwen3.5-4B (revision `851bf6e`), LoRA rank 16, alpha 32, the same 12 modules as Hopper.
+- Training: continued from Hopper 1.0's adapter on Hopper's decision tasks (at maintenance doses), general-purpose
+  sources (tabular record joins, CLINC150 intents, GSM8K arithmetic) and replay of public training data, with a fixed
+  retention constraint against Hopper 1.0 on a held-out replay bank.
+- Serving: identical to Hopper 1.1.1, including the calibration map and the long-menu shortlist (more than 26
+  options answered in two disclosed stages).
+
+## Evaluation (our runs)
+
+On our local run of the Decision Index 0.2 suite (40 benchmarks, A10G, same serving code, only the adapter
+differing):
+
+| | Hopper 1.1.1 | Hopper (G) 1.2 |
+| --- | ---: | ---: |
+| balanced raw | 52.74 | 53.50 |
+| balanced skill | 37.10 | 38.07 |
+| GSM8K | 0.318 | 0.480 |
+
+Paired bootstrap of the balanced-raw difference: +0.76 (95 % interval +0.55 to +0.98). Seed 1 (trained independently) confirms: balanced raw 53.44 vs 52.74 (+0.70), with every Index area at or above Hopper 1.1.1.
+Not official scores. Hopper (G) is not tuned for JevBench; we make no claim there.
+
+## Limitations
+
+- English, 4B parameters; it reads options, it does not generate reasoning.
+- Calibration uses Hopper 1.1.1's map, fitted for Hopper 1.0's adapter; it has not been refitted for these weights.
+- Research and demo use only (see above).

adapter_config.json

@@ -0,0 +1,59 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3_5ForCausalLM",
+    "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5"
+  },
+  "base_model_name_or_path": "Qwen/Qwen3.5-4B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "in_proj_qkv",
+    "q_proj",
+    "gate_proj",
+    "in_proj_z",
+    "in_proj_a",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "out_proj",
+    "in_proj_b"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8813cb2a1e44184bcdae017ace49cfc7cb00738c611423b6198c4b5ea553deaf
+size 129927008

hopper.json

@@ -0,0 +1,14 @@
+{
+ "kind": "per_kind",
+ "temperatures": {
+  "choice": 0.7898505975532796,
+  "noul": 0.7531284680253558,
+  "score": 0.8997033695617845
+ },
+ "fitted_on": {
+  "description": "our own held-out JevBench-style look-alike items, hard tier: three measurement files, 622 items, 536 on the axis. No JevBench item and no JevBench file.",
+  "tier": "hard",
+  "map": "per_kind",
+  "dropped_leakage_flagged": 66
+ }
+}